north-star-metric
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external documentation that could contain instructions intended to influence the agent's behavior.
- Ingestion points: Content is read from local files in directories such as product/, strategy/, metrics/, and analytics/, or from files explicitly provided via the @file syntax.
- Boundary markers: There are no explicit delimiters or specific instructions for the agent to isolate external data from its core instructions.
- Capability inventory: The skill is capable of searching for and reading local project files and using platform-specific commands like /context-save and /context-recall.
- Sanitization: There is no evidence of sanitization or validation of the input content before it is incorporated into the generated NSM documents.
Audit Metadata